BaoKien
/

my_awesome_qa_model

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

BaoKien commited on Jun 25, 2023

Commit

3630cd6

•

1 Parent(s): 629c489

update model card README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8691
 ## Model description
@@ -45,11 +45,11 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 25   | 2.7627          |
-| No log        | 2.0   | 50   | 1.8346          |
-| No log        | 3.0   | 75   | 1.8691          |
 ### Framework versions

 This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.9515
 ## Model description
 ### Training results
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.889         | 1.0   | 4380  | 0.8729          |
+| 0.6755        | 2.0   | 8760  | 0.8529          |
+| 0.4681        | 3.0   | 13140 | 0.9515          |
 ### Framework versions